🔌
New: connect Claude & other AIs to GenAIList over MCP — research the catalog and contribute to the shared knowledge base. Learn how →
// RUN — FITS
Can the GMKtec EVO-X3 run Jamba?
Yes — here's how fast and up to what context, with real measured numbers.
Jamba on the GMKtec EVO-X3
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 32k | 1.6-2 t/s | ~0.1-0.1 (slow) |
| Q8 | yes | 190k | 3.2-3.9 t/s | ~0.1-0.2 (slow) |
| Q4 | yes | 259k | 5.8-7 t/s | ~0.2-0.3 (slow) |
Estimate (memory-bound). Beyond "max context" the KV cache spills to SSD swap and speed drops to the "beyond" figure.
FAQ
Can the GMKtec EVO-X3 run Jamba?▶
Yes. At Q4 it generates ~5.8-7 tok/s and fits up to 259k context; beyond that it spills to SSD swap and slows to ~0.2-0.3 tok/s.
How much context fits?▶
At Q4, up to about 259k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.